pith. sign in

arxiv: 1805.12352 · v2 · pith:ZHWPDG4Znew · submitted 2018-05-31 · 💻 cs.CL · cs.AI· cs.LG· cs.NE

DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder

classification 💻 cs.CL cs.AIcs.LGcs.NE
keywords latentdialogwaedistributionpriorsimplevariableswassersteinconditional
0
0 comments X
read the original abstract

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior such as standard normal distribution, thereby restricting the generated responses to a relatively simple (e.g., unimodal) scope. In this paper, we propose DialogWAE, a conditional Wasserstein autoencoder~(WAE) specially designed for dialogue modeling. Unlike VAEs that impose a simple distribution over the latent variables, DialogWAE models the distribution of data by training a GAN within the latent variable space. Specifically, our model samples from the prior and posterior distributions over the latent variables by transforming context-dependent random noise using neural networks and minimizes the Wasserstein distance between the two distributions. We further develop a Gaussian mixture prior network to enrich the latent space. Experiments on two popular datasets show that DialogWAE outperforms the state-of-the-art approaches in generating more coherent, informative and diverse responses.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.